Title: Prediction method of product market demand based on Prophet random forest

Authors: Chaoyong Jia

Addresses: School of Mathematics and Physics, Bengbu University, Bengbu, Anhui, China

Abstract: This paper proposed a prediction method of product market demand based on Prophet random forest. After analysing the workflow of Prophet model, generate the random forest and its decision-making process and then pre-process the original data of product market through the process of data filling, feature standardisation and feature mapping, providing a reliable data basis for subsequent demand prediction. Then, the optimal subset selection algorithm is used to extract the product market demand characteristics, and the demand characteristics are input into Prophet random forest to realise the prediction of product market demand. The experimental results show that the prediction accuracy of the proposed method is 0.969, and the maximum prediction time in the experiment is only 14.9 s, and the waveform trend of the predicted result is roughly the same as that of the actual value, which highlights the effectiveness of the proposed method.

Keywords: Prophet model; random forest algorithm; optimal subset selection algorithm; product market demand; demand forecast.

DOI: 10.1504/IJPD.2024.137814

International Journal of Product Development, 2024 Vol.28 No.1/2, pp.60 - 72

Received: 24 Apr 2022
Accepted: 03 Oct 2022
Published online: 05 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article